arXiv AI
GALA: Geometry-Aware Language Model for Controllable Object Arrangement
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
Hugging Face Trending Papers
Oct 20
GALA: Geometry-Aware Language Model for Controllable Object Arrangement
Reasoning about fine-grained placement constraints, such as support and containment, is essential for realistic 3D scene creation. It remains a significant challenge for existing methods that rely on...
arXiv AI
Oct 26
SceneBloom: Agentic Indoor Environment Generation with Realistic and Diverse Layouts for Embodied Learning
SceneBloom is an agentic framework that generates realistic, varied, and simulation-ready indoor environments for embodied learning. It combines diffusion-based visual layout sampling with a contract-guided 3D compiler that uses extracted relations for geometric fitting and pose correction. The method outperforms baselines across five room types, achieving higher visual quality, physical stability, and better alignment with real room distributions, and improves object navigation policy success rates on real scans.
arXiv Computer Vision
Oct 1
SPOON: Towards Coherent Compositional 3D Scene Generation from Uncalibrated Multi-view Images
arXiv:2609.39590v1 Announce Type: new Abstract: Compositional 3D scene generation aims to recover complete 3D object shapes and their spatial arrangement from visual observations. Recent image-condit...
arXiv Computer Vision
Oct 22
VoxProg: 3D Spatial Reasoning through Voxel Programming
VoxProg introduces voxel programming for 3D spatial reasoning, enabling language models to translate task interpretations into executable programs that operate on local voxel views of scene surfaces. By indexing surface geometry on regular grids, the approach isolates task-relevant regions and boundaries, allowing downstream pose programs to compute target SE(3) poses. The method is evaluated on the 71-task VoxProg-Bench benchmark, showing consistent superiority over relation-based, keypoint-based, and mesh-based baselines.
arXiv Computation and Language
Sep 2
Apples on the Table? Evaluating Text-Guided 3D Scene Synthesis via Fine-Grained Constraint Verification
The paper introduces LEGO, a benchmark dataset pairing user text descriptions with human‑annotated fine‑grained constraints and reference 3D scenes, and LEGO‑Eval, an evaluation framework that decomposes descriptions into atomic constraints and verifies each using grounding and spatial reasoning tools. It demonstrates that LEGO‑Eval detects misalignment more accurately than existing methods and that current 3D scene synthesis approaches achieve at most a 10% success rate on this benchmark.
arXiv Computer Vision
Oct 21
Scene-R1: Video-Grounded Large Language Models for 3D Scene Reasoning with Lightweight Annotations
arXiv:2506.17545v2 Announce Type: replace Abstract: Large language models are increasingly being applied to 3D scene understanding. However, existing 3D-aware LLMs largely operate as black boxes: the...